OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Cerno Agentic Local Deep Research

Cerno Agentic Local Deep Research is an open-source, self-hosted workspace for multi-step research and analysis using AI agents. It decomposes complex queries into staged tasks, exposes workflow reasoning and progress for review, and organizes sources and generated outputs such as reports, code, and data. The documented application uses a Python/Django backend and React/Vite frontend, and supports cloud LLMs or local

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cerno Agentic Local Deep Research — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Cerno when a research question benefits from staged investigation and you want to inspect the agent workflow and its collected artifacts. Its self-hosted setup and local-model option also suit users seeking local control over research files.

Who it is for

  • Researchers conducting literature reviews, data extraction, or report preparation.
  • Developers and research teams who want to inspect and steer multi-agent workflows.
  • Analysts compiling findings from news, financial data, or social media.

Documented uses

  • Break a complex research question into a sequence of agent tasks.
  • Monitor task progress and inspect intermediate reasoning steps.
  • Organize sources and generated research artifacts for review.
  • Synthesize findings for literature reviews, market analysis, or competitor research.
Before you choose

Requirements & limits

The project is available as a public GitHub repository under the MIT License. The documented installation uses Docker Compose; the README lists Python 3.10+, Node.js 18+, and npm as prerequisites.

  • Cerno is a self-hosted application rather than a hosted research service; the documented setup requires local development/runtime prerequisites and Docker Compose.
  • The project describes both cloud LLM backends and local models through Ollama, so model choice affects whether prompts may be sent outside the machine.
  • The interface exposes task states and intermediate reasoning, which is relevant when researchers need to inspect how a result was produced.
  • The README identifies generated reports, code, data, and sources as tracked artifacts and names Markdown, Jupyter notebooks, and JSON as export formats.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Cerno with Docker Compose

Build and launch the documented local Cerno workspace.

Before you start

  • Python 3.10 or later
  • Node.js 18 or later and npm
  • Docker and Docker Compose
  • A clone of the Cerno repository

Steps

  1. Clone the repository.

  2. Create a .env file using .env.example as the template.

  3. Build and launch the application with docker-compose up --build.

  4. Open http://localhost:5173.

Expected outcome

The Cerno workspace is launched locally and can be opened in a browser at the documented address.

Guide limitations

  • The README gives setup instructions but does not detail the subsequent research workflow or model-provider configuration in this installation guide.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
24 October 2026
Original website title
Cerno-AI/Cerno-Agentic-Local-Deep-Research · Official homepage title · retained in its source language
How we review sourcesSuggest a correction